MIMD VERSUS SIMD COMPUTATION: EXPERIENCE WITH NON-NUMERIC PARALLEL ALGORITHMS

We focus on differences inherent in the design and implementation of non-numeric parallel algorithms on MIMD and SIMD architectures. We take as our prototypical examples time-space optimal merging and sorting routines. Our representative MIMD and SIMD machines are the Sequent Symmetry S81 and the Co...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Parallel algorithms and applications Ročník 2; číslo 1-2; s. 123 - 138
Hlavní autoři: BRESHEARS, CLAY P., LANGSTON, MICHAEL A.
Médium: Journal Article
Jazyk:angličtina
Vydáno: Taylor & Francis Group 01.01.1994
Témata:
architecture tradeoffs
C.4
F.2
KEY WORDS: Algorithm transmogrification
memory management
parallel computation
time-space optimality
ISSN:1063-7192
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:We focus on differences inherent in the design and implementation of non-numeric parallel algorithms on MIMD and SIMD architectures. We take as our prototypical examples time-space optimal merging and sorting routines. Our representative MIMD and SIMD machines are the Sequent Symmetry S81 and the Connection Machine CM-2, respectively. In addition to the contrast provided by their differing execution philosophies, this choice of machines allows us to compare results from both shared-memory and distributed-memory models. Unlike many numerical parallel algorithms, non-numeric parallel programs are rarely well structured with respect to inter-processor cooperation, memory access and communication patterns. This is particularly apparent when one must deal with delicate issues such as process synchronization in the MIMD model and coding variations in the SIMD model. Our experiences are highlighted with examples obtained during the process of MIMD to SIMD program transformation Unexpected events can occur when algorithms designed with one architectural style in mind are modified for execution on another. Timings and other measurements arc useful in identifying important bottlenecks. We discuss some relative strengths and weaknesses of the two competing models that have become evident during this transformation process.
ISSN:1063-7192
DOI:10.1080/10637199408915411